16 citations · 16 across the 6 of their papers we have counts for
6 papers
World Value Functions: Knowledge Representation for Multitask Reinforcement Learning
Geraud Nangue Tasse, Steven James, Benjamin Rosman
An open problem in artificial intelligence is how to learn and represent knowledge that is sufficient for a general agent that needs to solve multiple tasks in a given world. In th…
Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning
Nathan Michlo, Devon Jarvis, Richard Klein +1
In this work, we investigate the properties of data that cause popular representation learning approaches to fail. In particular, we find that in environments where states do not s…
Learning Abstract and Transferable Representations for Planning
Steven James, Benjamin Rosman, George Konidaris
We are concerned with the question of how an agent can acquire its own representations from sensory data. We restrict our focus to learning representations for long-term planning,…
Adaptive Online Value Function Approximation with Wavelets
Michael Beukman, Michael Mitchley, Dean Wookey +2
Using function approximation to represent a value function is necessary for continuous and high-dimensional state spaces. Linear function approximation has desirable theoretical gu…
Automatic Encoding and Repair of Reactive High-Level Tasks with Learned Abstract Representations
Adam Pacheck, Steven James, George Konidaris +1
We present a framework that, given a set of skills a robot can perform, abstracts sensor data into symbols that we use to automatically encode the robot's capabilities in Linear Te…
Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levels
Michael Beukman, Christopher W Cleghorn, Steven James
Procedurally generated video game content has the potential to drastically reduce the content creation budget of game developers and large studios. However, adoption is hindered by…